JP2009541848A5

JP2009541848A5 -

Info

Publication number: JP2009541848A5
Application number: JP2009516491A
Authority: JP
Filing date: 2007-05-29
Publication date: 2010-07-08

Claims

A method,
Dividing the computer processing job into a plurality of micro jobs including at least a first micro job and a second micro job ;
Executing the first micro job of the plurality of micro jobs;
Based at least in part on detecting that an amount of time between execution of the first microjob and the second microjob may exceed a minimum latency, the plurality of microjobs Executing a second micro .

Dividing the computing job to the plurality of micro-jobs are executed by the application program initiating the computer processing job A method according to claim 1.

The method of claim 1, wherein the minimum waiting time is a required idle time when one or more resources were idle.

The method of claim 1, wherein the minimum latency is a minimum amount of time to wait between execution of each microjob of the plurality of microjobs.

The step of executing the second microjob is further based on determining that there is no other application seeking access to the one or more resources other than the application having the second microjob. The method according to claim 1.

Further comprising executing a third microjob, wherein the third microjob is executed when the amount of time between execution for the second microjob and the third microjob is the Based at least in part on detecting that a second minimum amount of latency that is different from a minimum latency between execution of the first and second microjobs may be exceeded. The method of claim 1.

A method,
Dividing the computer processing job into a plurality of micro jobs including at least a first micro job and a second micro job;
Determining that utilization of the resource by one or more other jobs currently using the resource is lower than a first resource utilization threshold, wherein the resource executes the first microjob And the method further comprises:
Causing the first micro job to be executed based at least in part on determining that use of the resource by one or more other jobs currently using the resource is lower than the first resource use threshold; A method comprising steps.

8. The step of determining that usage of the resource by one or more other jobs that are currently using the resource is lower than a first resource usage threshold is performed by a micro job scheduler outside the operating system. The method described in 1.

8. The method of claim 7, wherein determining that the resource usage by one or more other jobs currently using the resource is lower than a first resource usage threshold is performed by an operating system.

Determining that usage of the resource by one or more other jobs currently using the resource is lower than a second resource usage threshold, wherein the resource executes the second micro job; And the method further comprises:
Causing the second micro-job to be executed based at least in part on determining that use of the resource by one or more other jobs currently using the resource is lower than the second resource utilization threshold; Including steps,
The method of claim 7, wherein the first resource utilization threshold for the resource is different from the second resource utilization threshold for the resource.

The step of causing execution of the previous SL first micro job is at least partially to limit the number of micro-jobs of the computing job that is executable before the other jobs to be able to utilize the resource The method according to claim 7 , which is based on.

The method of claim 11 , wherein the number of microjobs that are enabled is determined by examining computer resource utilization by a process other than the computer processing job .

Further comprising determining an amount of memory to be allocated to an application that initiates the computer processing job, wherein determining the amount of memory is not based on the memory required to run the application as a whole, The method of claim 7 , wherein the method is based at least in part on the much smaller amount of memory required to execute the micro-job of the application.

Further comprising the step of determining the amount of memory to be assigned to the application to start the computer processing job, determining the amount of said memory is at least partially based on the amount of memory available in the prior SL computer system The method according to claim 7 .

The micro job of the plurality of micro-jobs are part of the computer process, the execution of each micro-jobs can be delayed without affecting the results of the remaining portion of the computer process, to claim 7 The method described.

A computer readable medium carrying one or more sequences of instructions, wherein the one or more sequences of instructions are executed by one or more processors, the one or more processors from claim 1. A computer readable medium that causes the steps of the method of any one of 15 to be performed.

A system,
One or more processors;
16. A computer readable medium communicatively coupled to the one or more processors, wherein the computer readable medium is executed by the one or more processors. One or more stored sequences of instructions that cause the one or more processors to perform the method are stored.